SEARCH · Engineering Papers

Results for “Distributed System and Computing”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 361 records · Page 20

All sources NASA NTRS DOE OSTI

NASA NTRS2019

A Fast Monte Carlo Method for Model-Based Prognostics Based on Stochastic Calculus

This work proposes a fast Monte Carlo method to solve differential equations utilized in model-based prognostics. The methodology is derived from the theory of stochastic calculus, and the goal of such a method is to speed up the estimation of the probability density functions describing the independent variable evolution over time. In the prognostic scenarios presented in this paper, the stochastic differential equations describe variables directly or indirectly related to the degradation of a monitored system. The method allows the estimation of the probability density functions by solving the deterministic equation and approximating the stochastic integrals using samples of the model noise. By so doing, the prognostic problem is solved without the Monte Carlo simulation based on Euler's forward method, which is typically the most time consuming task of the prediction stage. Three different prognostic scenarios are presented as proof of concept: (i) life prediction of electrolytic capacitors, (ii) remaining time to discharge of Lithium-ion batteries, and (iii) prognostic of cracked structures under fatigue loading. The paper shows how the method produces probability density functions that are statistically indistinguishable from the distributions estimated with Euler's forward Monte Carlo simulation. However, the proposed solution is orders of magnitude faster when computing the time-to-failure distribution of the monitored system. The approach may enable complex real-time prognostics and health management solutions with limited computing power.

stochastic calculus↗

NASA NTRS1985

Parameter identification in distributed systems

This paper describes a method for the identification of the parameters entering into the equations of motion of distributed systems. Because the motion of distributed systems is described in terms of partial differential equations, these parameters are in general continuous functions of the spatial variables. For vibrating systems, these parameters ordinarily represent the mass, stiffness and damping distributions. In this paper, these distributions are expanded in terms of finite series of known functions of the spatial variables multiplied by undetermined coefficients. It is assumed that the nature of the equations of motion is known and that a limited number of eigenvalues and eigenfunctions is identified in advance. Use is then made of the least squares method, in conjunction with the eigenfunctions' orthogonality, to compute the undetermined coefficients, thus identifying the system distributed parameters. A method for the identification of the eigensolution is also presented. The procedure for the identification of the eigensolution and of the system parameters is demonstrated via a numerical example.

Baruh, H.↗

NASA NTRS2008

Compliance and Functional Testing of IEEE 1451.1 for NCAP-to-NCAP Communications in a Sensor Network

Distributed control in a networked environment is an irreplaceable feature in systems with remote sensors and actuators. Although distributed control was not originally designed to be networked, usage of off-the-shelf networking technologies has become so prevalent that control systems are desired to have access mechanisms similar to computer networks. However, proprietary transducer interfaces for network communications and distributed control overwhelmingly dominate this industry. Unless the lack of compatibility and interoperability among transducers is resolved, the mature level of access (that computer networking can deliver) will not be achieved in such networked distributed control systems. Standardization of networked transducer interfaces will enable devices from different manufacturers to talk to each other and ensure their plug-and-play capability. One such standard is the suite of IEEE 1451 for sensor network communication and transducer interfaces. The suite not only provides a standard interface for smart transducers, but also outlines the connection of an NCAP (network capable application processor) and transducers (through a transducer interface module TIM). This paper presents the design of the compliance testing of IEEE 1451.1 (referred to as Dot1) compatible NCAP-to-NCAP communications on a link-layer independent medium. The paper also represents the first demonstration of NCAP-to-NCAP communications with Dot1 compatibility: a tester NCAP and an NCAP under test (NUT).

Figueroa, Jorge↗

NASA NTRS2006

Implementing Access to Data Distributed on Many Processors

A reference architecture is defined for an object-oriented implementation of domains, arrays, and distributions written in the programming language Chapel. This technology primarily addresses domains that contain arrays that have regular index sets with the low-level implementation details being beyond the scope of this discussion. What is defined is a complete set of object-oriented operators that allows one to perform data distributions for domain arrays involving regular arithmetic index sets. What is unique is that these operators allow for the arbitrary regions of the arrays to be fragmented and distributed across multiple processors with a single point of access giving the programmer the illusion that all the elements are collocated on a single processor. Today's massively parallel High Productivity Computing Systems (HPCS) are characterized by a modular structure, with a large number of processing and memory units connected by a high-speed network. Locality of access as well as load balancing are primary concerns in these systems that are typically used for high-performance scientific computation. Data distributions address these issues by providing a range of methods for spreading large data sets across the components of a system. Over the past two decades, many languages, systems, tools, and libraries have been developed for the support of distributions. Since the performance of data parallel applications is directly influenced by the distribution strategy, users often resort to low-level programming models that allow fine-tuning of the distribution aspects affecting performance, but, at the same time, are tedious and error-prone. This technology presents a reusable design of a data-distribution framework for data parallel high-performance applications. Distributions are a means to express locality in systems composed of large numbers of processor and memory components connected by a network. Since distributions have a great effect on the performance of applications, it is important that the distribution strategy is flexible, so its behavior can change depending on the needs of the application. At the same time, high productivity concerns require that the user be shielded from error-prone, tedious details such as communication and synchronization.

James, Mark↗

DOE OSTI2025

I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey

Growing interest in Artificial Intelligence (AI) has resulted in a surge in demand for faster methods of Machine Learning (ML) model training and inference. This demand for speed has prompted the use of high performance computing (HPC) systems that excel in managing distributed workloads. Because data is the main fuel for AI applications, the performance of the storage and I/O subsystem of HPC systems is critical. In the past, HPC applications accessed large portions of data written by simulations or experiments or ingested data for visualizations or analysis tasks. ML workloads perform small reads spread across a large number of random files. This shift of I/O access patterns poses several challenges to modern parallel storage systems. In this paper, we survey I/O in ML applications on HPC systems, and target literature within a 6-year time window from 2019 to 2024. We define the scope of the survey, provide an overview of the common phases of ML, review available profilers and benchmarks, examine the I/O patterns encountered during offline data preparation, training, and inference, and explore I/O optimizations utilized in modern ML frameworks and proposed in recent literature. Lastly, we seek to expose research gaps that could spawn further R&D.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1980

Application of a reversible chemical reaction system to solar thermal power plants

Three distributed dish solar thermal power systems using various applications of SO2/SO3 chemical energy storage and transport technology were comparatively assessed. Each system features various roles for the chemical system: (1) energy storage only, (2) energy transport, or (3) energy transport and storage. These three systems were also compared with the dish-Stirling, using electrical transport and battery storage, and the central receiver Rankine system, with thermal storage, to determine the relative merit of plants employing a thermochemical system. As an assessment criterion, the busbar energy costs were compared. Separate but comparable solar energy cost computer codes were used for distributed receiver and central receiver systems. Calculations were performed for capacity factors ranging from 0.4 to 0.8. The results indicate that SO2/SO3 technology has the potential to be more cost effective in transporting the collected energy than in storing the energy for the storage capacity range studied (2-15 hours)

Hanseth, E. J.↗

DOE OSTI2024

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (distributed parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

graph algorithms, high performance comptuing↗

DOE OSTI2024

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (Distributed Parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve an optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively, the performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

Sattar, Naw Safrin↗

DOE OSTI2023

Assessing the Impact of Cybersecurity Attacks on Energy Systems

This paper investigates the cyber resiliency of future power systems with high penetration of distributed energy resources using advanced distributed and (or) hierarchical control architectures. Specifically, we simulate cyberattacks on three prototypical use cases, and we identify attack scenarios that are the most damaging to the overall system performance. We show that these attacks can have a significant impact on grid operation. Results provide additional insights into the robustness of the system to the most common cyberattacks.

buildings↗

DOE OSTI2024

A Microservices Architecture Toolkit for Interconnected Science Ecosystems

Microservices architecture is a promising approach for developing reusable scientific workflow capabilities for inte- grating diverse resources, such as experimental and observational instruments and advanced computational and data management systems, across many distributed organizations and facilities. In this paper, we describe how the INTERSECT Open Architec- ture leverages federated systems of microservices to construct interconnected science ecosystems, review how the INTERSECT software development kit eases microservice capability develop- ment, and demonstrate the use of such capabilities for deploying an example multi-facility INTERSECT ecosystem.

Brim, Michael↗

NASA NTRS1980

Development of Integrated Programs for Aerospace-vechicle Design (IPAD). IPAD user requirements: Implementation (first-level IPAD)

The requirements implementation strategy for first level development of the Integrated Programs for Aerospace Vehicle Design (IPAD) computing system is presented. The capabilities of first level IPAD are sufficient to demonstrated management of engineering data on two computers (CDC CYBER 170/720 and DEC VAX 11/780 computers) using the IPAD system in a distributed network environment.

Source record↗

NASA NTRS1984

Research in computer science

Several short summaries of the work performed during this reporting period are presented. Topics discussed in this document include: (1) resilient seeded errors via simple techniques; (2) knowledge representation for engineering design; (3) analysis of faults in a multiversion software experiment; (4) implementation of parallel programming environment; (5) symbolic execution of concurrent programs; (6) two computer graphics systems for visualization of pressure distribution and convective density particles; (7) design of a source code management system; (8) vectorizing incomplete conjugate gradient on the Cyber 203/205; (9) extensions of domain testing theory and; (10) performance analyzer for the pisces system.

Ortega, J. M.↗

NASA NTRS1985

Research in computer science

Synopses are given for NASA supported work in computer science at the University of Virginia. Some areas of research include: error seeding as a testing method; knowledge representation for engineering design; analysis of faults in a multi-version software experiment; implementation of a parallel programming environment; two computer graphics systems for visualization of pressure distribution and convective density particles; task decomposition for multiple robot arms; vectorized incomplete conjugate gradient; and iterative methods for solving linear equations on the Flex/32.

Ortega, J. M.↗

NASA NTRS1986

First 3 years of operation of RIACS (Research Institute for Advanced Computer Science) (1983-1985)

The focus of the Research Institute for Advanced Computer Science (RIACS) is to explore matches between advanced computing architectures and the processes of scientific research. An architecture evaluation of the MIT static dataflow machine, specification of a graphical language for expressing distributed computations, and specification of an expert system for aiding in grid generation for two-dimensional flow problems was initiated. Research projects for 1984 and 1985 are summarized.

Denning, P. J.↗

NASA NTRS1990

Balancing Loads Among Parallel Data Processors

Heuristic algorithm minimizes amount of memory used by multiprocessor system. Distributes load of many identical, short computations among multiple parallel digital data processors, each of which has its own (local) memory. Each processor operates on distinct and independent set of data in larger shared memory. As integral part of load-balancing scheme, total amount of space used in shared memory minimized. Possible applications include artificial neural networks or image processors for which "pipeline" and vector methods of load balancing inappropriate.

Baffes, Paul Thomas↗

NASA NTRS1991

Management of the Space Station Freedom onboard local area network

An operational approach is proposed to managing the Data Management System Local Area Network (LAN) on Space Station Freedom. An overview of the onboard LAN elements is presented first, followed by a proposal of the operational guidelines by which management of the onboard network may be effected. To implement the guidelines, a recommendation is then presented on a set of network management parameters which should be made available in the onboard Network Operating System Computer Software Configuration Item and Fiber Distributed Data Interface firmware. Finally, some implications for the implementation of the various network management elements are discussed.

Miller, Frank W.↗

NASA NTRS1993

Automated documentation generator for advanced protein crystal growth

The System Management and Production Laboratory at the Research Institute, the University of Alabama in Huntsville (UAH), was tasked by the Microgravity Experiment Projects (MEP) Office of the Payload Projects Office (PPO) at Marshall Space Flight Center (MSFC) to conduct research in the current methods of written documentation control and retrieval. The goals of this research were to determine the logical interrelationships within selected NASA documentation, and to expand on a previously developed prototype system to deliver a distributable, electronic knowledge-based system. This computer application would then be used to provide a paperless interface between the appropriate parties for the required NASA document.

Maddux, Gary A.↗

NASA NTRS1993

Distributed simulation using a real-time shared memory network

The Advanced Control Technology Branch of the NASA Lewis Research Center performs research in the area of advanced digital controls for aeronautic and space propulsion systems. This work requires the real-time implementation of both control software and complex dynamical models of the propulsion system. We are implementing these systems in a distributed, multi-vendor computer environment. Therefore, a need exists for real-time communication and synchronization between the distributed multi-vendor computers. A shared memory network is a potential solution which offers several advantages over other real-time communication approaches. A candidate shared memory network was tested for basic performance. The shared memory network was then used to implement a distributed simulation of a ramjet engine. The accuracy and execution time of the distributed simulation was measured and compared to the performance of the non-partitioned simulation. The ease of partitioning the simulation, the minimal time required to develop for communication between the processors and the resulting execution time all indicate that the shared memory network is a real-time communication technique worthy of serious consideration.

Simon, Donald L.↗